@inproceedings{das-etal-2025-video,
title = "Video-guided Machine Translation: A Survey of Models, Datasets, and Challenges",
author = "Das, Pinaki and
Singh, Virendra and
Bhattacharyya, Pushpak and
Haffari, Gholamreza",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.ijcnlp-long.178/",
pages = "3346--3356",
ISBN = "979-8-89176-298-5",
abstract = "In recent years, machine translation has evolved with the integration of multimodal information. Infusion of multi-modality into translation tasks decreases ambiguation and enhances translation scores. Common modalities include images, speech, and videos, which provide additional context alongside the text to be translated. While multimodal translation with images has been extensively studied, video-guided machine translation (VMT) has gained increasing attention, particularly since Wang et al. 2019 first explored this task. In this paper, we provide a comprehensive overview of VMT, highlighting its unique challenges, methodologies, and recent advancements. Unlike previous surveys that primarily focus on image-guided multimodal machine translation, this work explores the distinct complexities and opportunities introduced by adding video as a modality to the translation task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="das-etal-2025-video">
<titleInfo>
<title>Video-guided Machine Translation: A Survey of Models, Datasets, and Challenges</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pinaki</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Virendra</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-298-5</identifier>
</relatedItem>
<abstract>In recent years, machine translation has evolved with the integration of multimodal information. Infusion of multi-modality into translation tasks decreases ambiguation and enhances translation scores. Common modalities include images, speech, and videos, which provide additional context alongside the text to be translated. While multimodal translation with images has been extensively studied, video-guided machine translation (VMT) has gained increasing attention, particularly since Wang et al. 2019 first explored this task. In this paper, we provide a comprehensive overview of VMT, highlighting its unique challenges, methodologies, and recent advancements. Unlike previous surveys that primarily focus on image-guided multimodal machine translation, this work explores the distinct complexities and opportunities introduced by adding video as a modality to the translation task.</abstract>
<identifier type="citekey">das-etal-2025-video</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-long.178/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>3346</start>
<end>3356</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Video-guided Machine Translation: A Survey of Models, Datasets, and Challenges
%A Das, Pinaki
%A Singh, Virendra
%A Bhattacharyya, Pushpak
%A Haffari, Gholamreza
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-298-5
%F das-etal-2025-video
%X In recent years, machine translation has evolved with the integration of multimodal information. Infusion of multi-modality into translation tasks decreases ambiguation and enhances translation scores. Common modalities include images, speech, and videos, which provide additional context alongside the text to be translated. While multimodal translation with images has been extensively studied, video-guided machine translation (VMT) has gained increasing attention, particularly since Wang et al. 2019 first explored this task. In this paper, we provide a comprehensive overview of VMT, highlighting its unique challenges, methodologies, and recent advancements. Unlike previous surveys that primarily focus on image-guided multimodal machine translation, this work explores the distinct complexities and opportunities introduced by adding video as a modality to the translation task.
%U https://aclanthology.org/2025.ijcnlp-long.178/
%P 3346-3356
Markdown (Informal)
[Video-guided Machine Translation: A Survey of Models, Datasets, and Challenges](https://aclanthology.org/2025.ijcnlp-long.178/) (Das et al., IJCNLP-AACL 2025)
ACL
- Pinaki Das, Virendra Singh, Pushpak Bhattacharyya, and Gholamreza Haffari. 2025. Video-guided Machine Translation: A Survey of Models, Datasets, and Challenges. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 3346–3356, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.